Humera Tariq

Bio: Humera Tariq is an academic researcher from University of Karachi. The author has contributed to research in topics: Image segmentation & Fuzzy logic. The author has an hindex of 3, co-authored 17 publications receiving 75 citations.

K-Means Cluster Analysis for Image Segmentation

Abstract: K-Means reasonably divides the data into k groups is an important question that arises when one works on Image Segmentation? Which color space one should choose and how to ascertain that the k we determine is valid? The purpose of this study was to explore the answers to aforementioned questions. We perform K-Means on a number of 2-cluster, 3- cluster and k-cluster color images (k>3) in RGB and L*a*b* feature space. Ground truth (GT) images have been used to accomplish validation task. Silhouette analysis supports the peaks for given k-cluster image. Model accuracy in RGB space falls between 30% and 55% while in L*a*b* color space it ranges from 30% to 65%. Though few images used, but experimentation proves that K-Means significantly segment images much better in L*a*b* color space as compared to RGB feature space. Keywordsevaluation, L*a*b* Color Space, Precision Recall

A Portfolio Optimization Algorithm Using Fuzzy Granularity Based Clustering

Abstract: Clustering algorithms are applied to numerous problems in multiple domains including historic data analysis, financial markets analysis for portfolio optimization and image processing. Recent years have witnessed a surge in use of nature inspired computing (NIC) techniques for data clustering to solve various real world optimization problems. Granular Computing (GC) is an emerging technique to handle pieces of information, known as information granules. In this paper, an ensemble of fuzzy clustering using Particle Swarm Optimization and Granular computing for stock market portfolio optimization. The model is then tested on stocks listed in Hong Kong Stock Exchange. Experimental results suggested that clusters formed through Fuzzy Particle Swarm Optimization (FPSO) with Granular computing are well suited and efficient for portfolio optimization. For comparison, we have used a benchmark index of Hong Kong Stock Exchange called as Hang Sang Composite Index (HSCI). Results proved that results of proposed approach are better in comparison to benchmark results of HSCI.

Brain MRI literature review for interdisciplinary studies

Abstract: Computer science individuals, biomedical engineers and IT professionals require foundation knowledge about brain anatomical structures and physical sciences especially when it comes to research. The objective in this paper is to develop basic understanding of brain anatomical structure to be used for magnetic resonance imaging (MRI) and image processing along with necessary foundations to cultivate interdisciplinary research. The review incorporates the glorious history of MRI along with its marvelous mathematical contribution. This contribution makes the measurement of proton density possible which is then transformed into two dimensional magnetic resonance images for visualization and various brain related computer aided diagnostics and treatment. Spin physics, Magnetic field Precession, Larmor frequency, Bloch equation and Fourier Transform are the building blocks of magnetic resonance imaging. All the foundations which are compulsory and must be known at first sight to brain MRI are made available in this review.

Contour Extraction of Femur and Tibia Condyles on Plain Anteroposterior (AP) Radiograph

Abstract: of femur (F) and tibia (T) are key bony landmarks around the knee joint. The condyles contour extraction is the first key step towards: quantification of femorotibial (FT) joint space width (JSW), to assess FT joint space narrowing (JSN), to determine knee joint alignment angles and in defining the lateral and medial condyle radii. This paper aims to contour extraction of femur and tibia condyles on plain anteroposterior (AP) knee radiograph. A number of standard OA and non-OA AP radiographs in DICOM format are acquired. The images are resized and filtered to detect femoral and tibia condyles edge pixels respectively. Thresholding is then applied which introduce outliers. After removing outliers spline interpolation and smoothing is applied to trace and extract the femur and tibia contours. The results demonstrates promising extracted contours on non-OA and moderate OA radiographs but needs improvement in radiographs showing severe OA. The femur and tibia contours obtained are well localized, smooth and have no broken lines.

A Novel Image Dehazing and Assessment Method

Abstract: Images captured in hazy weather conditions often suffer from color contrast and color fidelity. This degradation is represented by transmission map which represents the amount of attenuation and airlight which represents the color of additive noise. In this paper, we have proposed a method to estimate the transmission map using haze levels instead of airlight color since there are some ambiguities in estimation of airlight. Qualitative and quantitative results of proposed method show competitiveness of the method given. In addition we have proposed two metrics which are based on statistics of natural outdoor images for assessment of haze removal algorithms.

The Essential Physics Of Medical Imaging

Abstract: Thank you very much for reading the essential physics of medical imaging. As you may know, people have search hundreds times for their chosen novels like this the essential physics of medical imaging, but end up in harmful downloads. Rather than enjoying a good book with a cup of tea in the afternoon, instead they juggled with some infectious virus inside their laptop. the essential physics of medical imaging is available in our digital library an online access to it is set as public so you can get it instantly. Our digital library saves in multiple countries, allowing you to get the most less latency time to download any of our books like this one. Merely said, the the essential physics of medical imaging is universally compatible with any devices to read.

Classification of 3D Digital Heritage

Abstract: In recent years, the use of 3D models in cultural and archaeological heritage for documentation and dissemination purposes is increasing. The association of heterogeneous information to 3D data by means of automated segmentation and classification methods can help to characterize, describe and better interpret the object under study. Indeed, the high complexity of 3D data along with the large diversity of heritage assets themselves have constituted segmentation and classification methods as currently active research topics. Although machine learning methods brought great progress in this respect, few advances have been developed in relation to cultural heritage 3D data. Starting from the existing literature, this paper aims to develop, explore and validate reliable and efficient automated procedures for the classification of 3D data (point clouds or polygonal mesh models) of heritage scenarios. In more detail, the proposed solution works on 2D data (“texture-based” approach) or directly on the 3D data (“geometry-based approach) with supervised or unsupervised machine learning strategies. The method was applied and validated on four different archaeological/architectural scenarios. Experimental results demonstrate that the proposed approach is reliable and replicable and it is effective for restoration and documentation purposes, providing metric information e.g. of damaged areas to be restored.